VRCT
VRCT(VRChat Chatbox Translator & Transcription)
Runssource: GitHubhomepagePythonNOASSERTIONcommit 429a593fca42
Python, NOASSERTION licensed. The project labels itself: osc, speech recognition, speech to text and vrchat.
VRCT runs. An Argusic agent installed it in 48 minutes and hit 6 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Python backend starts and completes full initialization (Whisper model, CTranslate2, OSC), Vite frontend builds and serves, all 936 pytest tests pass, OCR engine is ready with downloaded models, Rust toolchain installed; Tauri native build blocked by missing webkit2gtk-4.1 system libraries (not installable without root).
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 60 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.

What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- pyaudiowpatch==0.2.12.6 has no Linux wheel (Windows-only WASAPI PortAudio bindings)8 minutes
- Tauri requires webkit2gtk-4.1, javascriptcoregtk-4.1, and libsoup-3.0 development libraries to build (missing system-wide)5 minutes
- models/clipboard/clipboard.py unconditionally tries ctypes.WinDLL for user32/kernel32 on all platforms3 minutes
- tools/chatbox_sample_player.py raises RuntimeError('Interactive playback requires Windows') unconditionally on non-Windows, even for --dry-run and --start which never call msvcrt3 minutes
- src-ui/import uses lowercase vrct.svg but the file is uppercase VRCT.svg (Windows case-insensitive vs Linux case-sensitive FS)2 minutes
- test_clipboard_focus_and_paste.py::test_copies_and_pastes_when_focus_succeeds expects focus/paste path that is gated on sys.platform == 'win32' and never runs on Linux1 minute
- Install time
- 48 minutes
- Cold machine to finish
- 25 minutes
- Errors hit and fixed
- 6 hit, 6 fixed with no human help
- How the result was proved
- pytest src-python/test/ exited 0 with 936 passed; vite build completed (dist/ with index.html and assets); npm run vite-preview answered HTTP 200 on port 4317; python src-python/mainloop.py completed initialization and emitted /run/initialization_complete; OCR fetch and engine verification succeeded; curl -s -o /dev/null -w '%{http_code}' http://127.0.0.1:4317/ returned 200
- Model tokens used
- 1,727,111
- Exact commit tested
- 429a593fca42
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
Watch the session
The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.
A recording of attempt 2, run , the attempt that decided the verdict above. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
=== Whisper transcription test ===
Traceback (most recent call last):
File "<string>", line 4, in <module>
File "/work/repo/.venv/lib/python3.12/site-packages/faster_whisper/transcribe.py", line 834, in t…
audio = decode_audio(audio, sampling_rate=sampling_rate)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
=== test_data directory ===
no test_data dir
Now I have everything I need. Let me compile the final ARGUSIC_RESULT JSON.
tokens used
1,727,111
Now I have everything I need. Let me compile the final ARGUSIC_RESULT JSON.Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Installed in 48 minutes.
- Recovered from all 6 errors without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- Its license file could not be classified automatically, so check it yourself before using it.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Runs | 100.00 | 0.33 | |
| Argusic Runner | 1/3 | Did not run | 20.00 | 0.23 |
Topics (from GitHub)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/vrct)Questions
- Does VRCT run?
- Yes. VRCT runs. Argusic installed and launched it on a clean machine in 48 minutes, hitting 6 errors on the way, and recorded the session.
- How did Argusic test VRCT?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 429a593fca42. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test VRCT?
- The run that produced this verdict cost $0.33: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does VRCT take to install?
- 48 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does VRCT need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing VRCT?
- 6 things broke in the recorded run, and 6 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for VRCT?
- All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.